agentleFS
dexio-wikidexio-wiki/llm-wiki-skills/skills/wiki-query/SKILL.md

wiki-query

Skill1 starsChanged 47 days agoMITView on GitHub

Answer a question from an LLM wiki: find and read the relevant pages, answer with the page paths you relied on, check anything mutable at its original source, say plainly what the wiki does not cover, and file substantial answers back as query pages so the research compounds. Use when a person asks something the wiki may cover, or after an answer took real research.

41 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-update, wiki-research and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bozhouDevSkill

    wiki-update

    Use when revising existing wiki pages because knowledge has changed, a new piece of information updates or contradicts existing content, or the user wants to directly edit wiki content with LLM assistance.

    Also in 9 projects that use this

  • Ivy-Chen1999Skill

    wiki-research

    Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X", "find everything about Y", "do a deep dive on Z", "autonomous research on X", or wants comprehensive, web-sourced knowledge on a topic filed directly into their wiki.

    Also in 4 projects that use this

  • bozhouDevSkill

    wiki-init

    Use when bootstrapping a new personal wiki for any knowledge domain — research, codebase documentation, reading notes, competitive analysis, or any long-term knowledge accumulation project.

    Also in 7 projects that use this

  • Ivy-Chen1999Skill

    claude-history-ingest

    Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.

    Also in 3 projects that use this

  • nathanadaySkill

    almagest

    Orient in the Almagest vault, say what waits for the user, do the work a request asks in a linked repository, and route any other request to the skill that owns it. Use for /almagest, what is going on, status, what waits for me, where do I work on X, work on X, fix this, implement, build, note this, remember to, publish my journal, what is in my journals, and any request when the right skill is not clear. Keeping part of this conversation is wiki-save; files to learn from are wiki-ingest.

    Also in 3 projects that use this

  • +4 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check mutable facts at their source: before presenting them as current: prices, configuration, account state, who holds a role, anything …

    line 22
  2. Distinctive:

    File the answer back when it is substantial: If the answer needed several pages, outside research, or a judgment worth keeping, write it as …

    line 29

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Answer from a wiki

A wiki earns its upkeep when answers come from it faster and better than from scratch, and when good answers are kept so the next question starts further ahead.

Steps

  1. Orient on the question (wiki-orient): search two or three phrasings, read the canonical page and the neighbors that bear on it.
  2. Answer from what you read, and cite it. Give the page paths the answer rests on. If you combine pages, say so. If a page's claim carries a trust label (vendor-sourced, estimate, unverified), carry the label into the answer.
  3. Check mutable facts at their source before presenting them as current: prices, configuration, account state, who holds a role, anything with a date older than the decision it will feed. Say what you checked. If the source disagrees with the wiki, the answer uses the source and the wiki gets fixed (wiki-record or wiki-conflicts).
  4. Say what the wiki does not cover. "The wiki has nothing on X" is a useful answer; a plausible guess presented as if it came from the wiki is a harmful one. If you fill the gap from outside research, mark which parts came from where.
  5. File the answer back when it is substantial. If the answer needed several pages, outside research, or a judgment worth keeping, write it as a query page (below). Trivial lookups are not filed.
  6. Fix what you found on the way. A broken link, a stale date, a missing link between two pages you needed together: fix it with a small edit and a note, or report it.

Query page

Under queries/ (or where the schema puts them), named for the question:

---
title: Which vendors include SSO on their base plan?
description: One line with the short answer, not the question.
created: YYYY-MM-DD
updated: YYYY-MM-DD
type: query
tags: [...]
sources: [pages and URLs consulted]
confidence: high | medium | low
---

# Which vendors include SSO on their base plan?

Question (who asked, date).

## Short answer
Two to four sentences.

## Evidence
What was consulted, with links to wiki pages and sources, and the numbers that carry the
answer.

## Confidence and gaps
What would change the answer, and what was not checked.

Link the query page from the pages it draws on when it adds something they lack, so the answer is found from the topic and not only by search. When a follow-up question arrives in the same thread, add it as a section of the same query page rather than a new page.

Pitfalls

  • Answering from memory with the wiki open. If you did not read it in the wiki or a source this session, it is unverified; say so.
  • Citing a page for a claim the page does not make. Quote or paraphrase closely enough that the reader can find the sentence.
  • Filing every answer. A queries/ folder full of one-line lookups buries the real syntheses.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.